Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, non-destructive and open-world, but the description adds material context they cannot: live contract read, a 422 plus no charge for a non-ERC-20 address, $0.01/call pricing with 25 free calls, and that repeats are billed (which explains idempotentHint=false). The only gap is the response shape/pagination, which is minor here.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and return fields, then usage, then input format, then cost. The pricing sentence is dense but carries decision-relevant information; nothing is pure filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by naming the four returned fields. Combined with input formats, error behavior, and cost model, an agent has everything needed to call this correctly on the first try.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema: the argument accepts a ticker alias as well as a 0x address, a concrete example address is shown, and the error behavior for a non-contract address is stated.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Look up the name, symbol, decimals and total supply of an ERC-20 token contract on Celo'), names the exact returned fields, and explicitly separates itself from the sibling celo_token_balance. An agent can route correctly without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives two concrete use cases ('identify an unknown token address', 'format raw amounts') and names the alternative with the condition that selects it ('for a holder's balance use celo_token_balance'). It also flags the failure mode for a non-ERC-20 address, which is guidance an agent needs before choosing this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.